What is project-skill?

A project-specific instruction template for building and maintaining a knowledge graph, a connected collection of notes about entities and ideas. It describes sources, concepts, pages, naming, and the process for updating them.

Use it as a starting point for defining how a project ingests articles, papers, transcripts, or notes and turns them into linked wiki pages.

The provided text contains placeholders rather than details about a particular project. It therefore offers a general workflow but cannot explain a specific subject area.

project-skill — Skill for Claude Code by Ethics03/kgskill

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Ethics03/kgskill --skill init

Clone the repo

git clone --depth 1 https://github.com/Ethics03/kgskill

Made for: Claude Code.

Or install mykg, the plugin that ships this one along with the rest of its 3 skills, 6 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ethics03/kgskill/init/github.svg)](https://agentmods.dev/skills/ethics03/kgskill/init)

Your own site

<a href="https://agentmods.dev/skills/ethics03/kgskill/init"><img src="https://agentmods.dev/badge/skills/ethics03/kgskill/init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ethics03/kgskill/init"><img src="https://agentmods.dev/badge/skills/ethics03/kgskill/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 418 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.00418
Opus 5.5	$0.00009	$0.00167
Sonnet 5.5	$0.00005	$0.00084
Haiku 4.5	$0.00002	$0.00042

Measured 1mo ago against content hash 8ac657bda0f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

project-templates/init/SKILL.md · 84 lines

What it actually says

[PROJECT NAME] Skill

Project-specific instructions for the Knowledge Graph.

Project Overview

[Brief description of the project, domain, or topic]

Domain

[What domain is this project about? Examples:

Research: "Quantum computing research"
Reading: "The Lord of the Rings"
Personal: "Health and fitness tracking"
Code: "Codebase documentation" ]

Source Types

[What types of sources will be ingested?]

Articles
Papers
Transcripts
Notes
[Other]

Key Entities

[What kinds of entities are relevant to this domain? Examples:

People, organizations, tools, places
Characters, locations, items
Concepts, frameworks, methods ]

Key Concepts

[What concepts are central to this domain?]

Ingestion Workflow

[Custom steps for ingesting sources in this domain]

Read source
Extract entities and concepts
Create/update wiki pages
Note contradictions with existing knowledge
Update index and log

Page Types

[Project-specific page types beyond the standard entities/concepts/synthesis]

Conventions

[Project-specific naming and formatting conventions]

File Naming

Entities: entity-name.md
Concepts: concept-name.md
Sources: source-title-slug.md

Cross-References

Link to related entities: [[entities/Related]]
Link to concepts: [[concepts/Topic]]

Current Focus

See [[../Active.md]] for current focus items.

Key Files

File	Purpose
`raw/`	Source documents
`wiki/entities/`	Entity pages
`wiki/concepts/`	Concept pages
`wiki/synthesis/`	High-level summaries
`../Active.md`	Current priorities

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 84 lines · 23 tokens per session scan A 8ac657bda0f2

Subscribe to this mod's changes

project-skill is a skill published in the GitHub repository Ethics03/kgskill (3 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 418 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Memory and context Writing and docs agent-skills knowledge-graph obsidian opencode skills

agent-recall

Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface: 6 tools with --full (adds checkaction); 13 tools with AREXTRAS=1 --full. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail…

Goldentrii/AgentRecall-X · 172 tokens

obsidian-memory-architecture

Use when designing, setting up, or maintaining an Obsidian vault as Hermes Agent's durable knowledge layer. Routes facts, conversation history, documents, procedures, and daily logs to the correct Hermes or vault system without duplicating everything into the prompt.

AtlasOmnia/hermes-custom-pack · 56 tokens

swarmvault

Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…

swarmclawai/swarmvault · 76 tokens

project-skill